In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Low-light is an inescapable element of our daily surroundings that greatly affects the efficiency of our vision. Research works on low-light has seen a steady growth, particularly in the field of image enhancement, but there is still a lack of a go-to database as benchmark. Besides, research fields that may assist us in low-light environments, such as object detection, has glossed over this aspect even though breakthroughs-after-breakthroughs had been achieved in recent years, most noticeably from the lack of low-light data (less than 2% of the total images) in successful public benchmark dataset such as PASCAL VOC, ImageNet, and Microsoft COCO. Thus, we propose the Exclusively Dark dataset to elevate this data drought, consisting exclusively of ten different types of low-light images (i.e. low, ambient, object, single, weak, strong, screen, window, shadow and twilight) captured in visible light only with image and object level annotations. Moreover, we share insightful findings in regards to the effects of low-light on the object detection task by analyzing visualizations of both hand-crafted and learned features. Most importantly, we found that the effects of low-light reaches far deeper into the features than can be solved by simple "illumination invariance'". It is our hope that this analysis and the Exclusively Dark dataset can encourage the growth in low-light domain researches on different fields. The Exclusively Dark dataset with its annotation is available at this https URL

Getting to Know Low-light Images with The Exclusively Dark Dataset

Palmprint processes a number of unique features for reliable personal recognition. However, different types of palmprint images contain different dominant features. Instead, only some features of the palmprint are visible in a palmprint image, whereas the other features may not be notable. For example, the low-resolution palmprint image has visible principal lines and wrinkles. By contrast, the high-resolution palmprint image contains clear ridge patterns and minutiae points. In addition, the three dimensional (3-D) palmprint image possesses curvatures of the palmprint surface. So far, there is no work to summarize the feature extraction of different types of palmprint images. In this paper, we have an aim to completely study the feature extraction and recognition of palmprint. We propose to use a unified framework to classify palmprint images into four categories: 1) the contact-based; 2) contactless; 3) high-resolution; and 4) 3-D palmprint images. Then, we analyze the motivations and theories of the representative extraction and matching methods for different types of palmprint images. Finally, we compare and test the state-of-the-art methods via the widely used palmprint databases, and point out some potential directions for future research.

Feature Extraction Methods for Palmprint Recognition: A Survey and Evaluation

Images captured under poor illumination conditions often exhibit characteristics such as low brightness, low contrast, a narrow gray range, and color distortion, as well as considerable noise, which seriously affect the subjective visual effect on human eyes and greatly limit the performance of various machine vision systems. The role of low-light image enhancement is to improve the visual effect of such images for the benefit of subsequent processing. This paper reviews the main techniques of low-light image enhancement developed over the past decades. First, we present a new classification of these algorithms, dividing them into seven categories: gray transformation methods, histogram equalization methods, Retinex methods, frequency-domain methods, image fusion methods, defogging model methods and machine learning methods. Then, all the categories of methods, including subcategories, are introduced in accordance with their principles and characteristics. In addition, various quality evaluation methods for enhanced images are detailed, and comparisons of different algorithms are discussed. Finally, the current research progress is summarized, and future research directions are suggested.

/pdf/an-experiment-based-review-of-low-light-image-enhancement-5dhscyutxx.pdf

An Experiment-Based Review of Low-Light Image Enhancement Methods

A hybrid optimization algorithm based on cuckoo search and differential evolution for solving constrained engineering problems

Densely connected convolutional transformer for single image dehazing

Sentiment analysis is an intellectual way of identifying users' sentiments towards certain entities. Natural Language Processing (NLP) has the process of analyzing sentiments as one of its prominent fields. NLP is a branch of computer science and artificial intelligence that deals with human-computer language interaction. The growth in e-commerce has led to increasing customer reviews about various products which are available on the internet. These product reviews offer a massive amount of valuable information which can be used for various decision- making purposes. Several methods have been developed in recent years in order to accomplish this task. In this paper, we discuss various levels of sentiment analysis followed by comparison among different approaches to sentiment analysis.

A Study on Sentiment Analysis of Product Reviews

Images clicked under low and non-uniform light conditions are visually unpleasant and lose details. Low-light images also impact the performance and thus reduce the effectiveness of various computer vision tasks. Thus numerous methods have been put forward in the past to upgrade the quality of low-light images. The innovations in the field of deep learning have paved the way for the application of neural networks to the task of enhancing low-light images. In this paper, we offer a comparative analysis of various approaches using deep learning for enhancing low-light images. We explore retinex based methods including KinD and RDGAN, and other non-retinex based methods including LLNet, GLAD Net, and Zero-DCE. We measure the effectiveness of these methods on various datasets and provide their advantages and disadvantages.

A Comparative Analysis of Deep Learning based Approaches for Low-Light Image Enhancement

Sketches have been employed since the ancient era of cave paintings for simple illustrations to represent real-world entities. The abstract nature and varied artistic styling makes automatic recognition of drawings more challenging than other areas of image classification. Moreover, the representation of sketches as a sequence of strokes instead of raster images introduces them at the correct abstract level. However, dealing with images as a sequence of small information makes it challenging. In this paper, we propose a Transformer-based network, dubbed as TransSketchNet, for sketch recognition. This architecture incorporates ordinal information to perform the classification task in real-time through vector images.

TransSketchNet: Attention-Based Sketch Recognition Using Transformers.

This paper presents an optimal fuzzy filter for Gaussian noise in color images using Bacterial Foraging Algorithm (BFA) and cosine similarity. The filter makes use of the relationship between different color components of a pixel to remove the noise from the color images. The adaptive cosine similarity between the central pixel and the neighboring pixels is estimated using color pairs red-green, red-blue and green-blue for noise removal. The membership function Large is defined and used to fuzzify similarity of each color component. Mean Square Error is used as an objective function for the bacterial foraging algorithm to learn the parameters of membership function Large. The correction term for the Gaussian filter is calculated using weighted average of the weights of all the neighboring pixels. The proposed Gaussian filter is found to be effective in eliminating noise from color images with the significant improvement in image quality. The experimental result on several color images proves the efficacy of the proposed fuzzy filter.

Anil Singh Parihar

Papers

Densely connected convolutional transformer for single image dehazing

A Study on Sentiment Analysis of Product Reviews

A Comparative Analysis of Deep Learning based Approaches for Low-Light Image Enhancement

TransSketchNet: Attention-Based Sketch Recognition Using Transformers.

An optimal fuzzy filter for Gaussian noise in color images using bacterial foraging algorithm